AI agents call devbox_project_list to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about existing Docker projects and their status without creating, modifying, deleting, or executing any changes. It is a passive reconnaissance operation that has no side effects. Given the homelab context, the blast radius of misuse is low—an agent could enumerate projects but cannot alter infrastructure.
From the tool's definition Tool description states it 'Scan[s] a base path for docker-compose projects and show[s] git remote + container status for each' — purely informational actions (scan, show) with no modification, deletion, or execution of operations.
Attacks that exploit this kind of access
Scan a base path for docker-compose projects and show git remote + container status for each. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for devbox_project_list: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Homelab. Nothing to install.
devbox_project_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the devbox_project_list rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for devbox_project_list. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
devbox_project_list is provided by the Homelab MCP server (nainounen/homelab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →